Skip to content

Translation in progress Some entries still include text in the original language.

Oct 12 · Monday

All papers

Found 8 papers
Filter4

Attack type

Jailbreaks7Prompt injection4

Attack technique

Automated search3

Impact

Harmful content8Unauthorized actions95Data and privacy leaks22Output manipulation50Availability and reliability4Oversight failure6

System type

AI Agent7

Attacker access

Black-box3White-box3

Attack surface / entry point

User input220Documents and messages0Tool responses7Memory writes2Images, audio and video50Training data20Weights and gradients26Distribution channels4

Layer

Application layer7
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 232papers have no tags yet and are not included in filtered results.
Impact：Harmful contentAttack surface / entry point：Documents and messagesAttack surface / entry point：Tool responsesAttack surface / entry point：Memory writesClear all

Another 232papers do not have category tags yet and are not included in filtered results.

  2. Evaluation and benchmarksarXiv 2610.07089

    研究者提出统一滥用监控基准，覆盖分解攻击与提示注入约 6200 条轨迹

    提出危害窗口与区间指标，统一评测分解攻击和提示注入下的智能体滥用监视

    arXiv
    2610.07089
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Gemma 4 26B-A4B, Qwen3.6 27B, Qwen3.5 27B and others12

    Abstract统一智能体滥用监视框架，动作视角兼顾两类威胁但危害定位仍存瓶颈。

    Paper analysisRead analysis
  3. Evaluation and benchmarksarXiv 2609.27336

    CART：面向大语言模型的闭环自适应红队框架

    提出闭环自适应红队框架 CART，评测模型与 Agent 的安全失败

    arXiv
    2609.27336
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Claude Opus 4.8, GPT-5.5, Grok 4.3 and others7
    AbstractCART 把红队做成可审计的闭环搜索，在三类评测上比静态回放发现更多失败与更高平均风险。

    CART 把自动红队从一次清单式打分，改成带预算、可追溯的闭环搜索。

    Paper analysisRead analysis
  4. OtherarXiv 2609.12413

    SoK 综述：智能体 AI 时代的越狱攻击、防御与实践考量

    系统梳理智能体执行链路中的越狱攻击与防御并比较推理时防御

    arXiv
    2609.12413
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Qwen3.5-4B, Llama-3.1-8B-Instruct
    AbstractSoK 将越狱重放到智能体流水线，并用两种模型检验回复层防御的边际与代价。

    Mia 等人把越狱安全从单轮回复扩展到智能体的规划、记忆、工具和智能体间通信，并问既有结论在更强原生对齐下是否还成立。

    Paper analysisRead analysis
  7. AttacksarXiv 2601.05466

    Jailbreaking large language models through reinforcement learning with iterative tool disguise attacks

    提出 iMIST，用工具伪装和 PPO 迭代越狱大语言模型

    arXiv
    2601.05466
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Attacker
    Black-box
    Evaluated models
    DeepSeek-V3, Qwen3-32B, GPT-OSS-120B
    AbstractiMIST 用工具伪装和在线 PPO 做黑盒越狱，Table I 中 JADES 高于同格基线。

    iMIST是黑盒越狱方法：把恶意查询伪装成合法工具调用，再用在线强化学习把响应的有害性分数往上推。

    Paper analysisRead analysis
You have reached the end